Entities recognised in the resolutions of the States General of the Dutch Republic (1576-1796)

Update 2025-03-24: A new version has been released with (a new set of paragraph texts has also been released, see https://doi.org/10.5281/zenodo.15074656).

These files contain curated sets of recognised entities in the resolutions of the States General of the Dutch Republic between 1576 and 1796. The following entity types are present:

Abbreviation
Name
Description

COM
Commissies
Internal committees of the States General

DAT
Datums
Dates referencing other resolutions

HOE
Hoedanigheden
Roles and functions of persons

LOC
Locaties
Geographical locations

ORG
Organisaties
Organisations, Institutions, Polities

PER
Persoonsnamen
Personal names

Associated with every entity type except DAT are two files: one containing entities and entity metadata, the other containing the annotations on the text of the resolutions that point to forementioned entities.

The entity metadata files contain the following fields:

Field
Description

id
Identifier linking entities to annotations

name
Canonical name

comment
Additional information

category
Entity type

labels
Entity categories

links
Links to external datasets

geo_data
Geographical information (LOC only)

The annotation files contain the following fields:

Field
Description

reference
Identifies the annotated text fragment

entity
Entity identifier (not for DAT)

date
Referenced date (DAT only)

provenance
Provenance of the entity assignment

Update 2025-02-11: The raw NER output is now also included. There is one file per entity type, with 8 fields:

Field
Description

layer
Entity type

inv
Inventory Number (book identifier)

resolution_id
resolution identifier (identifies the resolution in the corresponding book)

paragraph_id
paragraph identifier (corresponds to a paragraph in the resolution)

tag_text
the text string that was tagged as an entity

offset
the character offset of the text string in the paragraph

end
the character end offset of the text string

tag_length
the character length of the text string